martin_create_pr

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint=true, and the description adds valuable context about the preview mode (execute=false) versus actual creation. This clarifies idempotency and safety considerations beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is a single sentence, very concise and front-loaded. It efficiently communicates the core purpose and key usage point, though it could be slightly expanded without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, oneOf constraint, output schema), the description is too minimal. It omits explanation of parameter selection logic, format options, and the role of sibling tools, leaving the agent with insufficient context for correct use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description only mentions the 'execute' parameter. It fails to explain the purpose of other parameters like base, file, loopId, latest, format, runsDir, or the oneOf constraint, leaving the agent with insufficient guidance for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Create or preview' and the resource 'GitHub PR with MartinLoop dossier body'. It distinguishes from sibling tools like martin_pr_summary and martin_review_pr by specifying PR creation with a dossier body and a preview mode.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides guidance on using execute=true to actually call gh versus previewing, but does not explicitly state when to use this tool over alternatives or when not to use it. No mention of prerequisites or context-specific recommendations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.